通过特征分布匹配提升半监督对比学习的分类精度
Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data
- 引入标签与无标签数据特征分布匹配机制
- 在多个数据集上实现更高图像分类准确率
- 适合关注半监督学习优化的研究者
深度学习的发展显著提升了图像分类性能。然而，数据标注成本高昂，促使研究转向无监督学习方法，如对比学习。在真实场景中，完全无标签的数据集罕见，因此少量标注数据与大量无标签数据共存的半监督学习（SSL）更具实际意义。一种经典的半监督对比学习方法是为无标签数据分配伪标签。本研究旨在通过在标签与无标签特征嵌入之间引入分布匹配，改进基于伪标签的半监督学习，从而提升多种数据集上的图像分类准确率。
原文摘要 · Abstract (English)
The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world scenarios, fully unlabeled datasets are rare, making semi-supervised learning (SSL) highly relevant in scenarios where a small amount of labeled data coexists with a large volume of unlabeled data. A well-known semi-supervised contrastive learning approach involves assigning pseudo-labels to unlabeled data. This study aims to enhance pseudo-label-based SSL by incorporating distribution matching between labeled and unlabeled feature embeddings to improve image classification accuracy across multiple datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。